[Openmp-commits] [openmp] 16064e7 - [OpenMP] Reset async stream properly upon failure

[via Openmp-commits]

Author: Joseph Huber
Date: 2021-03-26T19:05:06-04:00
New Revision: 16064e71e934547ca68b3d8f4bd71e9a2b7f4248

URL: https://github.com/llvm/llvm-project/commit/16064e71e934547ca68b3d8f4bd71e9a2b7f4248
DIFF: https://github.com/llvm/llvm-project/commit/16064e71e934547ca68b3d8f4bd71e9a2b7f4248.diff

LOG: [OpenMP] Reset async stream properly upon failure

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.

Reviewers: jdoerfert

Differential Revision: https://reviews.llvm.org/D99443

Added: 
    

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

Removed: 
    


################################################################################
diff  --git a/openmp/libomptarget/plugins/cuda/src/rtl.cpp b/openmp/libomptarget/plugins/cuda/src/rtl.cpp
index 3d0424f16037..a2f3cf4ba0c8 100644
--- a/openmp/libomptarget/plugins/cuda/src/rtl.cpp
+++ b/openmp/libomptarget/plugins/cuda/src/rtl.cpp
@@ -1035,13 +1035,6 @@ class DeviceRTLTy {
   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
@@ -1050,7 +1043,13 @@ class DeviceRTLTy {
                                 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;
   }
 };