maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[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
This commit is contained in:
Joseph Huber 2022-07-21 14:12:01 -04:00
parent 5102084787
commit e82e07d74a
1 changed files with 7 additions and 24 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
openmp/libomptarget/DeviceRTL/CMakeLists.txt
View File

@ -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.