[Openmp-commits] [PATCH] D99510: [OpenMP] Trim error messages in CUDA plugin

[Joseph Huber via Phabricator via Openmp-commits]

jhuber6 created this revision.
jhuber6 added a reviewer: jdoerfert.
Herald added subscribers: guansong, yaxunl.
jhuber6 requested review of this revision.
Herald added subscribers: openmp-commits, sstefan1.
Herald added a project: OpenMP.

Remove some of the error messages printed when the CUDA plugin fails. The current error messages can be confusing because they are the first error messages printed after the async stream finds an error. This means that the printed values aren't related to what caused the issue, but are simply the last asyncronous operation that succeeded on the device. Remove these as they can be misleading.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D99510

Files:
  openmp/docs/design/Runtimes.rst
  openmp/libomptarget/plugins/cuda/src/rtl.cpp


Index: openmp/libomptarget/plugins/cuda/src/rtl.cpp
===================================================================
--- openmp/libomptarget/plugins/cuda/src/rtl.cpp
+++ openmp/libomptarget/plugins/cuda/src/rtl.cpp
@@ -114,9 +114,9 @@
       cuMemcpyDtoDAsync((CUdeviceptr)DstPtr, (CUdeviceptr)SrcPtr, Size, Stream);
 
   if (Err != CUDA_SUCCESS) {
-    REPORT("Error when copying data from device to device. Pointers: src "
-           "= " DPxMOD ", dst = " DPxMOD ", size = %" PRId64 "\n",
-           DPxPTR(SrcPtr), DPxPTR(DstPtr), Size);
+    DP("Error when copying data from device to device. Pointers: src "
+       "= " DPxMOD ", dst = " DPxMOD ", size = %" PRId64 "\n",
+       DPxPTR(SrcPtr), DPxPTR(DstPtr), Size);
     CUDA_ERR_STRING(Err);
     return OFFLOAD_FAIL;
   }
@@ -823,9 +823,9 @@
 
     Err = cuMemcpyHtoDAsync((CUdeviceptr)TgtPtr, HstPtr, Size, Stream);
     if (Err != CUDA_SUCCESS) {
-      REPORT("Error when copying data from host to device. Pointers: host "
-             "= " DPxMOD ", device = " DPxMOD ", size = %" PRId64 "\n",
-             DPxPTR(HstPtr), DPxPTR(TgtPtr), Size);
+      DP("Error when copying data from host to device. Pointers: host "
+         "= " DPxMOD ", device = " DPxMOD ", size = %" PRId64 "\n",
+         DPxPTR(HstPtr), DPxPTR(TgtPtr), Size);
       CUDA_ERR_STRING(Err);
       return OFFLOAD_FAIL;
     }
@@ -845,9 +845,9 @@
 
     Err = cuMemcpyDtoHAsync(HstPtr, (CUdeviceptr)TgtPtr, Size, Stream);
     if (Err != CUDA_SUCCESS) {
-      REPORT("Error when copying data from device to host. Pointers: host "
-             "= " DPxMOD ", device = " DPxMOD ", size = %" PRId64 "\n",
-             DPxPTR(HstPtr), DPxPTR(TgtPtr), Size);
+      DP("Error when copying data from device to host. Pointers: host "
+         "= " DPxMOD ", device = " DPxMOD ", size = %" PRId64 "\n",
+         DPxPTR(HstPtr), DPxPTR(TgtPtr), Size);
       CUDA_ERR_STRING(Err);
       return OFFLOAD_FAIL;
     }
@@ -897,10 +897,9 @@
       if (Err == CUDA_SUCCESS)
         return OFFLOAD_SUCCESS;
 
-      REPORT("Error returned from cuMemcpyPeerAsync. src_ptr = " DPxMOD
-             ", src_id =%" PRId32 ", dst_ptr = " DPxMOD ", dst_id =%" PRId32
-             "\n",
-             DPxPTR(SrcPtr), SrcDevId, DPxPTR(DstPtr), DstDevId);
+      DP("Error returned from cuMemcpyPeerAsync. src_ptr = " DPxMOD
+         ", src_id =%" PRId32 ", dst_ptr = " DPxMOD ", dst_id =%" PRId32 "\n",
+         DPxPTR(SrcPtr), SrcDevId, DPxPTR(DstPtr), DstDevId);
       CUDA_ERR_STRING(Err);
     }
 
@@ -1044,9 +1043,9 @@
     AsyncInfo->Queue = nullptr;
 
     if (Err != CUDA_SUCCESS) {
-      REPORT("Error when synchronizing stream. stream = " DPxMOD
-             ", async info ptr = " DPxMOD "\n",
-             DPxPTR(Stream), DPxPTR(AsyncInfo));
+      DP("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;
Index: openmp/docs/design/Runtimes.rst
===================================================================
--- openmp/docs/design/Runtimes.rst
+++ openmp/docs/design/Runtimes.rst
@@ -220,7 +220,6 @@
 
 .. code-block:: text
 
-    CUDA error: Error when copying data from device to host.
     CUDA error: an illegal memory access was encountered 
     Libomptarget error: Copying data from device failed.
     Libomptarget error: Call to targetDataEnd failed, abort target.


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D99510.333878.patch
Type: text/x-patch
Size: 3518 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/openmp-commits/attachments/20210329/590b2c61/attachment.bin>