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
@@ -21,6 +21,7 @@
 #include <SourceInfo.h>
 
 #define OFFLOAD_SUCCESS (0)
+#define OFFLOAD_EVENT_NOT_READY 600
 #define OFFLOAD_FAIL (~0)
 
 #define OFFLOAD_DEVICE_DEFAULT -1
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
@@ -151,18 +151,22 @@
 // 2) Record the event based on the status of \p AsyncInfo->Queue at the moment
 // of function call to __tgt_rtl_record_event. An event becomes "meaningful"
 // once it is recorded, such that others can depend on it.
-// 3) Call __tgt_rtl_wait_event to set dependence on the event. Whether the
+// 3) Call __tgt_rtl_query_event to query the status of all work currently
+// captured by an event
+// 4) Call __tgt_rtl_wait_event to set dependence on the event. Whether the
 // operation is blocking or non-blocking depends on the target. It is expected
 // to be non-blocking, just set dependence and return.
-// 4) Call __tgt_rtl_sync_event to sync the event. It is expected to block the
+// 5) Call __tgt_rtl_sync_event to sync the event. It is expected to block the
 // thread calling the function.
-// 5) Destroy the event (__tgt_rtl_destroy_event).
+// 6) Destroy the event (__tgt_rtl_destroy_event).
 // {
 int32_t __tgt_rtl_create_event(int32_t ID, void **Event);
 
 int32_t __tgt_rtl_record_event(int32_t ID, void *Event,
                                __tgt_async_info *AsyncInfo);
 
+int32_t __tgt_rtl_query_event(int32_t ID, void *Event);
+
 int32_t __tgt_rtl_wait_event(int32_t ID, void *Event,
                              __tgt_async_info *AsyncInfo);
 
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
@@ -28,6 +28,7 @@
   CUDA_SUCCESS = 0,
   CUDA_ERROR_INVALID_VALUE = 1,
   CUDA_ERROR_INVALID_HANDLE = 400,
+  CUDA_ERROR_NOT_READY = 600,
 } CUresult;
 
 typedef enum CUstream_flags_enum {
@@ -258,6 +259,7 @@
 
 CUresult cuEventCreate(CUevent *, unsigned int);
 CUresult cuEventRecord(CUevent, CUstream);
+CUresult cuEventQuery(CUevent);
 CUresult cuStreamWaitEvent(CUstream, CUevent, unsigned int);
 CUresult cuEventSynchronize(CUevent);
 CUresult cuEventDestroy(CUevent);
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
@@ -71,6 +71,7 @@
 
 DLWRAP(cuEventCreate, 2);
 DLWRAP(cuEventRecord, 2);
+DLWRAP(cuEventQuery, 1);
 DLWRAP(cuStreamWaitEvent, 3);
 DLWRAP(cuEventSynchronize, 1);
 DLWRAP(cuEventDestroy, 1);
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
@@ -159,6 +159,24 @@
   return OFFLOAD_SUCCESS;
 }
 
+int queryEvent(void *EventPtr) {
+  CUevent Event = reinterpret_cast<CUevent>(EventPtr);
+  CUresult Err = cuEventQuery(Event);
+
+  if (Err == CUDA_ERROR_NOT_READY) {
+    DP("Captured work is incomplete. Event = " DPxMOD "\n", DPxPTR(Event));
+    return OFFLOAD_EVENT_NOT_READY;
+  }
+
+  if (Err != CUDA_SUCCESS) {
+    DP("Error when querying an event. Event = " DPxMOD "\n", DPxPTR(Event));
+    CUDA_ERR_STRING(Err);
+    return OFFLOAD_FAIL;
+  }
+
+  return OFFLOAD_SUCCESS;
+}
+
 int syncEvent(void *EventPtr) {
   CUevent Event = reinterpret_cast<CUevent>(EventPtr);
 
@@ -1621,11 +1639,16 @@
                                __tgt_async_info *async_info_ptr) {
   assert(async_info_ptr && "async_info_ptr is nullptr");
   assert(async_info_ptr->Queue && "async_info_ptr->Queue is nullptr");
-  assert(event_ptr && "event_ptr is nullptr");
+  assert(event_ptr && "event is nullptr");
 
   return recordEvent(event_ptr, async_info_ptr);
 }
 
+int32_t __tgt_rtl_query_event(int32_t device_id, void *event_ptr) {
+  assert(event_ptr && "event is nullptr");
+  return queryEvent(event_ptr);
+}
+
 int32_t __tgt_rtl_wait_event(int32_t device_id, void *event_ptr,
                              __tgt_async_info *async_info_ptr) {
   assert(DeviceRTL.isValidDeviceId(device_id) && "device_id is invalid");
diff --git a/openmp/libomptarget/plugins/exports b/openmp/libomptarget/plugins/exports
--- a/openmp/libomptarget/plugins/exports
+++ b/openmp/libomptarget/plugins/exports
@@ -26,6 +26,7 @@
     __tgt_rtl_print_device_info;
     __tgt_rtl_create_event;
     __tgt_rtl_record_event;
+    __tgt_rtl_query_event;
     __tgt_rtl_wait_event;
     __tgt_rtl_sync_event;
     __tgt_rtl_destroy_event;
diff --git a/openmp/libomptarget/src/device.h b/openmp/libomptarget/src/device.h
--- a/openmp/libomptarget/src/device.h
+++ b/openmp/libomptarget/src/device.h
@@ -250,6 +250,7 @@
   bool IsInit;
   std::once_flag InitFlag;
   bool HasPendingGlobals;
+  bool HasEventSupport;
 
   HostDataToTargetListTy HostDataToTargetMap;
   PendingCtorsDtorsPerLibrary PendingCtorsDtors;
@@ -356,6 +357,9 @@
   /// Create an event.
   int32_t createEvent(void **Event);
 
+  /// query the status of an event.
+  int32_t queryEvent(void *Event);
+
   /// Record the event based on status in AsyncInfo->Queue at the moment the
   /// function is called.
   int32_t recordEvent(void *Event, AsyncInfoTy &AsyncInfo);
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
@@ -21,8 +21,10 @@
 
 DeviceTy::DeviceTy(RTLInfoTy *RTL)
     : DeviceID(-1), RTL(RTL), RTLDeviceID(-1), IsInit(false), InitFlag(),
-      HasPendingGlobals(false), HostDataToTargetMap(), PendingCtorsDtors(),
-      ShadowPtrMap(), DataMapMtx(), PendingGlobalsMtx(), ShadowMtx() {}
+      HasPendingGlobals(false),
+      HasEventSupport(RTL->create_event ? true : false), HostDataToTargetMap(),
+      PendingCtorsDtors(), ShadowPtrMap(), DataMapMtx(), PendingGlobalsMtx(),
+      ShadowMtx() {}
 
 DeviceTy::~DeviceTy() {
   if (DeviceID == -1 || !(getInfoLevel() & OMP_INFOTYPE_DUMP_TABLE))
@@ -561,6 +563,13 @@
   return OFFLOAD_SUCCESS;
 }
 
+int32_t DeviceTy::queryEvent(void *Event) {
+  if (RTL->query_event)
+    return RTL->query_event(RTLDeviceID, Event);
+
+  return OFFLOAD_SUCCESS;
+}
+
 int32_t DeviceTy::waitEvent(void *Event, AsyncInfoTy &AsyncInfo) {
   if (RTL->wait_event)
     return RTL->wait_event(RTLDeviceID, Event, AsyncInfo);
diff --git a/openmp/libomptarget/src/rtl.h b/openmp/libomptarget/src/rtl.h
--- a/openmp/libomptarget/src/rtl.h
+++ b/openmp/libomptarget/src/rtl.h
@@ -59,6 +59,7 @@
   typedef void(set_info_flag_ty)(uint32_t);
   typedef int32_t(create_event_ty)(int32_t, void **);
   typedef int32_t(record_event_ty)(int32_t, void *, __tgt_async_info *);
+  typedef int32_t(query_event_ty)(int32_t, void *);
   typedef int32_t(wait_event_ty)(int32_t, void *, __tgt_async_info *);
   typedef int32_t(sync_event_ty)(int32_t, void *);
   typedef int32_t(destroy_event_ty)(int32_t, void *);
@@ -102,6 +103,7 @@
   print_device_info_ty *print_device_info = nullptr;
   create_event_ty *create_event = nullptr;
   record_event_ty *record_event = nullptr;
+  query_event_ty *query_event = nullptr;
   wait_event_ty *wait_event = nullptr;
   sync_event_ty *sync_event = nullptr;
   destroy_event_ty *destroy_event = nullptr;
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
@@ -187,6 +187,7 @@
         dlsym(dynlib_handle, "__tgt_rtl_create_event");
     *((void **)&R.record_event) =
         dlsym(dynlib_handle, "__tgt_rtl_record_event");
+    *((void **)&R.query_event) = dlsym(dynlib_handle, "__tgt_rtl_query_event");
     *((void **)&R.wait_event) = dlsym(dynlib_handle, "__tgt_rtl_wait_event");
     *((void **)&R.sync_event) = dlsym(dynlib_handle, "__tgt_rtl_sync_event");
     *((void **)&R.destroy_event) =