[OpenMP] Reset async stream properly upon failure

[jhuber6]

Summary

If the call to synchronize fails, it will currently block the stream indefinitely if execution is continued from this point. Additionally, if the program exits it will trigger an assertion on the non-null value of the async queue and prevent the runtime from printing debugging information.

[jdoerfert]

LGTM.

openmp/libomptarget/plugins/cuda/src/rtl.cpp

DP("Launch of entry point at " DPxMOD " successful!\n",
        DPxPTR(TgtEntryPtr));
 
     return OFFLOAD_SUCCESS;
   }
 
   int synchronize(const int DeviceId, __tgt_async_info *AsyncInfo) const {
     CUstream Stream = reinterpret_cast<CUstream>(AsyncInfo->Queue);
     CUresult Err = cuStreamSynchronize(Stream);
-    if (Err != CUDA_SUCCESS) {
-      REPORT("Error when synchronizing stream. stream = " DPxMOD
-             ", async info ptr = " DPxMOD "\n",
-             DPxPTR(Stream), DPxPTR(AsyncInfo));
-      CUDA_ERR_STRING(Err);
-      return OFFLOAD_FAIL;
-    }
 
     // Once the stream is synchronized, return it to stream pool and reset
     // AsyncInfo. This is to make sure the synchronization only works for its
     // own tasks.
     StreamManager->returnStream(DeviceId,
                                 reinterpret_cast<CUstream>(AsyncInfo->Queue));
     AsyncInfo->Queue = nullptr;
 
-    return OFFLOAD_SUCCESS;
+    if (Err != CUDA_SUCCESS) {
+      REPORT("Error when synchronizing stream. stream = " DPxMOD
+             ", async info ptr = " DPxMOD "\n",
+             DPxPTR(Stream), DPxPTR(AsyncInfo));
+      CUDA_ERR_STRING(Err);
+    }
+    return (Err == CUDA_SUCCESS) ? OFFLOAD_SUCCESS : OFFLOAD_FAIL;
   }
 };
 
 DeviceRTLTy DeviceRTL;
 } // namespace
 
 // Exposed library API function
 #ifdef __cplusplus