[PATCH] D47804: [CUDA] Replace 'nv_weak' attributes in CUDA headers with 'weak'.

[Artem Belevich via Phabricator via cfe-commits]

tra created this revision.
tra added reviewers: Hahnfeld, aaron.ballman, jlebar.
Herald added subscribers: bixia, sanjoy.

An alternative to implementing nv_weak attribute (https://reviews.llvm.org/D47201).

The patch should make runtime sub functions to have .weak attribute in PTX and that should avoid GPU-side linking errors.


https://reviews.llvm.org/D47804

Files:
  clang/lib/Headers/__clang_cuda_runtime_wrapper.h


Index: clang/lib/Headers/__clang_cuda_runtime_wrapper.h
===================================================================
--- clang/lib/Headers/__clang_cuda_runtime_wrapper.h
+++ clang/lib/Headers/__clang_cuda_runtime_wrapper.h
@@ -100,11 +100,17 @@
 #include "host_config.h"
 #include "host_defines.h"
 
+// Temporarily replace "nv_weak" with weak, so __attribute__((nv_weak)) in
+// cuda_device_runtime_api.h ends up being __attribute__((weak)) which is the
+// functional equivalent of what we need.
+#pragma push_macro("nv_weak")
+#define nv_weak weak
 #undef __CUDABE__
 #undef __CUDA_LIBDEVICE__
 #define __CUDACC__
 #include "cuda_runtime.h"
 
+#pragma pop_macro("nv_weak")
 #undef __CUDACC__
 #define __CUDABE__
 


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D47804.150055.patch
Type: text/x-patch
Size: 724 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/cfe-commits/attachments/20180605/5b25f3ac/attachment.bin>