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

[Libomptarget] Do not use retaining attributes for the static library 

When we build the libomptarget device runtime library targeting bitcode,
we need special care to make sure that certain functions are not
optimized out. This is because we manually internalize and optimize
these definitions, ignoring their standard linkage semantics. When we
build with the static library, we can maintain these semantics and we do
not need these to be kept-alive. Furthermore, if they are kept-alive it
prevents them from being removed during LTO. This prevents us from
completely internalizing `IsSPMDMode` and removing several other
functions. This patch removes these for the static library target by
using a macro definition to enable them.

Reviewed By: JonChesterfield

Differential Revision: https://reviews.llvm.org/D126701
This commit is contained in:
Joseph Huber 2022-05-31 10:08:25 -04:00
parent a083f3caa1
commit 421b1f55c6
4 changed files with 11 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
openmp/libomptarget/DeviceRTL/CMakeLists.txt
View File

@ -234,12 +234,12 @@ 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 -Xclang -target-feature -Xclang +ptx61 "-D__CUDA_ARCH__=${sm}0")
compileDeviceRTLLibrary(sm_${sm} nvptx -target nvptx64-nvidia-cuda -DLIBOMPTARGET_BC_TARGET -Xclang -target-feature -Xclang +ptx61 "-D__CUDA_ARCH__=${sm}0")
endforeach()
add_custom_target(omptarget.devicertl.amdgpu)
foreach(mcpu ${amdgpu_mcpus})
compileDeviceRTLLibrary(${mcpu} amdgpu -target amdgcn-amd-amdhsa -D__AMDGCN__ -nogpulib)
compileDeviceRTLLibrary(${mcpu} amdgpu -target amdgcn-amd-amdhsa -DLIBOMPTARGET_BC_TARGET -D__AMDGCN__ -nogpulib)
endforeach()
set(LIBOMPTARGET_LLVM_VERSION "${LLVM_VERSION_MAJOR}.${LLVM_VERSION_MINOR}.${LLVM_VERSION_PATCH}")

7
openmp/libomptarget/DeviceRTL/include/Types.h
View File

@ -209,6 +209,13 @@ enum OMPTgtExecModeFlags : int8_t {
#define CONSTANT(NAME) \
NAME [[clang::loader_uninitialized, clang::address_space(4)]]
// Attribute to keep alive certain definition for the bitcode library.
#ifdef LIBOMPTARGET_BC_TARGET
#define KEEP_ALIVE __attribute__((used, retain))
#else
#define KEEP_ALIVE
#endif
///}
#endif

2
openmp/libomptarget/DeviceRTL/src/Mapping.cpp
View File

@ -276,7 +276,7 @@ uint32_t mapping::getNumberOfProcessorElements() {
// TODO: This is a workaround for initialization coming from kernels outside of
// the TU. We will need to solve this more correctly in the future.
int __attribute__((used, retain, weak)) SHARED(IsSPMDMode);
int __attribute__((weak)) KEEP_ALIVE SHARED(IsSPMDMode);
void mapping::init(bool IsSPMD) {
if (mapping::isInitialThreadInLevel0(IsSPMD))

2
openmp/libomptarget/DeviceRTL/src/Utils.cpp
View File

@ -21,7 +21,7 @@ using namespace _OMP;
namespace _OMP {
/// Helper to keep code alive without introducing a performance penalty.
__attribute__((used, retain, weak, optnone, cold)) void keepAlive() {
__attribute__((weak, optnone, cold)) KEEP_ALIVE void keepAlive() {
__kmpc_get_hardware_thread_id_in_block();
__kmpc_get_hardware_num_threads_in_block();
__kmpc_get_warp_size();