[Openmp-commits] [openmp] 2933845 - [OpenMP] Trim error messages in CUDA plugin

[via Openmp-commits]

Author: Joseph Huber
Date: 2021-03-29T12:20:19-04:00
New Revision: 29338459fb7e5f063ec5c22bd4aa0067647317cf

URL: https://github.com/llvm/llvm-project/commit/29338459fb7e5f063ec5c22bd4aa0067647317cf
DIFF: https://github.com/llvm/llvm-project/commit/29338459fb7e5f063ec5c22bd4aa0067647317cf.diff

LOG: [OpenMP] Trim error messages in CUDA plugin

Summary:
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.

Reviewers: jdoerfert

Differential Revision: https://reviews.llvm.org/D99510

Added: 
    

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

Removed: 
    


################################################################################
diff  --git a/openmp/docs/design/Runtimes.rst b/openmp/docs/design/Runtimes.rst
index ad36e43eccdc..7f281a6d5cb3 100644
--- a/openmp/docs/design/Runtimes.rst
+++ b/openmp/docs/design/Runtimes.rst
@@ -220,7 +220,6 @@ going wrong.
 
 .. 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.

diff  --git a/openmp/libomptarget/plugins/cuda/src/rtl.cpp b/openmp/libomptarget/plugins/cuda/src/rtl.cpp
index a2f3cf4ba0c8..25c80ee6021b 100644
--- a/openmp/libomptarget/plugins/cuda/src/rtl.cpp
+++ b/openmp/libomptarget/plugins/cuda/src/rtl.cpp
@@ -114,9 +114,9 @@ int memcpyDtoD(const void *SrcPtr, void *DstPtr, int64_t Size,
       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 @@ class DeviceRTLTy {
 
     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 @@ class DeviceRTLTy {
 
     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 @@ class DeviceRTLTy {
       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 @@ class DeviceRTLTy {
     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;