[Libomptarget] Build the DeviceRTL BC using clang directly

Currently the bitcode library is build using the clang front-end
manually. This was originally done because we did not support device
only compilation. Now we support device only compilation, at least for a
single offloading toolchain, so we can instead use clang directly rather
than using the front-end. This saves us needing to define things like
`aux_triple`.

Reviewed By: tianshilei1992

Differential Revision: https://reviews.llvm.org/D130293

diff --git a/openmp/libomptarget/DeviceRTL/CMakeLists.txt b/openmp/libomptarget/DeviceRTL/CMakeLists.txt
index 3ac3f59..0c74006 100644 (file)
--- a/openmp/libomptarget/DeviceRTL/CMakeLists.txt
+++ b/openmp/libomptarget/DeviceRTL/CMakeLists.txt
@@ -43,21 +43,6 @@ else()
   return()
 endif()
 
-# TODO: This part needs to be refined when libomptarget is going to support
-# Windows!
-# TODO: This part can also be removed if we can change the clang driver to make
-# it support device only compilation.
-if(CMAKE_HOST_SYSTEM_PROCESSOR MATCHES "x86_64")
-  set(aux_triple x86_64-unknown-linux-gnu)
-elseif(CMAKE_HOST_SYSTEM_PROCESSOR MATCHES "ppc64le")
-  set(aux_triple powerpc64le-unknown-linux-gnu)
-elseif(CMAKE_HOST_SYSTEM_PROCESSOR MATCHES "aarch64")
-  set(aux_triple aarch64-unknown-linux-gnu)
-else()
-  libomptarget_say("Not building DeviceRTL: unknown host arch: ${CMAKE_HOST_SYSTEM_PROCESSOR}")
-  return()
-endif()
-
 set(devicertl_base_directory ${CMAKE_CURRENT_SOURCE_DIR})
 set(include_directory ${devicertl_base_directory}/include)
 set(source_directory ${devicertl_base_directory}/src)
@@ -91,7 +76,6 @@ if (DEFINED LIBOMPTARGET_AMDGCN_GFXLIST)
   set(amdgpu_mcpus ${LIBOMPTARGET_AMDGCN_GFXLIST})
 endif()
 
-
 # Activate RTL message dumps if requested by the user.
 set(LIBOMPTARGET_DEVICE_DEBUG FALSE CACHE BOOL
   "Activate DeviceRTL debug messages.")
@@ -130,11 +114,10 @@ set (LIBOMPTARGET_LLVM_INCLUDE_DIRS_DEVICERTL "${LIBOMPTARGET_LLVM_INCLUDE_DIRS}
 list(TRANSFORM LIBOMPTARGET_LLVM_INCLUDE_DIRS_DEVICERTL PREPEND "-I")
 
 # Set flags for LLVM Bitcode compilation.
-set(bc_flags -S -x c++ -std=c++17 -fvisibility=hidden
-              ${clang_opt_flags}
-             -Xclang -emit-llvm-bc
-             -Xclang -aux-triple -Xclang ${aux_triple}
-             -fopenmp -fopenmp-cuda-mode -Xclang -fopenmp-is-device
+set(bc_flags -c -emit-llvm -std=c++17 -fvisibility=hidden
+              ${clang_opt_flags} --offload-device-only
+             -nocudalib -nogpulib -nostdinc
+             -fopenmp -fopenmp-cuda-mode
              -I${include_directory}
              -I${devicertl_base_directory}/../include
              ${LIBOMPTARGET_LLVM_INCLUDE_DIRS_DEVICERTL}
@@ -158,7 +141,7 @@ function(compileDeviceRTLLibrary target_cpu target_name)
     add_custom_command(OUTPUT ${outfile}
       COMMAND ${CLANG_TOOL}
       ${bc_flags}
-      -Xclang -target-cpu -Xclang ${target_cpu}
+      --offload-arch=${target_cpu}
       ${target_bc_flags}
       ${infile} -o ${outfile}
       DEPENDS ${infile} ${include_files}
@@ -229,12 +212,12 @@ endfunction()
 # Generate a Bitcode library for all the compute capabilities the user requested
 add_custom_target(omptarget.devicertl.nvptx)
 foreach(sm ${nvptx_sm_list})
-  compileDeviceRTLLibrary(sm_${sm} nvptx -target nvptx64-nvidia-cuda -DLIBOMPTARGET_BC_TARGET -Xclang -target-feature -Xclang +ptx61 "-D__CUDA_ARCH__=${sm}0")
+  compileDeviceRTLLibrary(sm_${sm} nvptx -fopenmp-targets=nvptx64-nvidia-cuda -DLIBOMPTARGET_BC_TARGET --cuda-feature=+ptx61)
 endforeach()
 
 add_custom_target(omptarget.devicertl.amdgpu)
 foreach(mcpu ${amdgpu_mcpus})
-  compileDeviceRTLLibrary(${mcpu} amdgpu -target amdgcn-amd-amdhsa -DLIBOMPTARGET_BC_TARGET -D__AMDGCN__ -nogpulib)
+  compileDeviceRTLLibrary(${mcpu} amdgpu -fopenmp-targets=amdgcn-amd-amdhsa -DLIBOMPTARGET_BC_TARGET -D__AMDGCN__ -nogpulib)
 endforeach()
 
 # Set the flags to build the device runtime from clang.