[Mlir-commits] [mlir] 6402706 - [mlir] Fix the link of libcuda.so in MLIRGPUTransforms to not use fully qualified path (#74018)

[llvmlistbot at llvm.org]

Author: Mehdi Amini
Date: 2023-11-30T19:30:05-08:00
New Revision: 6402706a00e806aef62836cd1a13a412349121eb

URL: https://github.com/llvm/llvm-project/commit/6402706a00e806aef62836cd1a13a412349121eb
DIFF: https://github.com/llvm/llvm-project/commit/6402706a00e806aef62836cd1a13a412349121eb.diff

LOG: [mlir] Fix the link of libcuda.so in MLIRGPUTransforms to not use fully qualified path (#74018)

At the moment we find libcuda.so in a path like:

  /usr/local/cuda/targets/x86_64-linux/lib/stubs/libcuda.so

and directly add this to `target_link_libraries`. The problem is that
our installed MLIR package will include the full path to the library,
and a user downstream when including our cmake installed package will
inherit this full path.

We're changing this to instead

 -L /usr/local/cuda/targets/x86_64-linux/lib/stubs/ -lcuda

Added: 
    

Modified: 
    mlir/lib/Dialect/GPU/CMakeLists.txt

Removed: 
    


################################################################################
diff  --git a/mlir/lib/Dialect/GPU/CMakeLists.txt b/mlir/lib/Dialect/GPU/CMakeLists.txt
index b76d18e81246eb1..e8b69879ad6a7ed 100644
--- a/mlir/lib/Dialect/GPU/CMakeLists.txt
+++ b/mlir/lib/Dialect/GPU/CMakeLists.txt
@@ -135,11 +135,15 @@ if(MLIR_ENABLE_CUDA_RUNNER)
     ${CMAKE_CUDA_TOOLKIT_INCLUDE_DIRECTORIES}
   )
 
+  # Add link path for the cuda driver library.
   find_library(CUDA_DRIVER_LIBRARY cuda HINTS ${CMAKE_CUDA_IMPLICIT_LINK_DIRECTORIES} REQUIRED)
+  get_filename_component(CUDA_DRIVER_LIBRARY_PATH "${CUDA_DRIVER_LIBRARY}" DIRECTORY)
+  target_link_directories(MLIRGPUTransforms PRIVATE ${CUDA_DRIVER_LIBRARY_PATH})
+
   target_link_libraries(MLIRGPUTransforms
     PRIVATE
     MLIRNVVMToLLVMIRTranslation
-    ${CUDA_DRIVER_LIBRARY}
+    cuda
   )
 
 endif()