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

[OpenMP] Expand short verisions of OpenMP offloading triples 

The OpenMP offloading libraries are built with fixed triples and linked
in during compile time. This would cause un-helpful errors if the user
passed in the wrong expansion of the triple used for the bitcode
library. because we only support these triples for OpenMP offloading we
can normalize them to the full verion used in the bitcode library.

Reviewed By: jdoerfert, JonChesterfield

Differential Revision: https://reviews.llvm.org/D117634
This commit is contained in:
Joseph Huber 2022-01-19 14:52:08 -05:00
parent d93ffa1b37
commit 28d718602a
3 changed files with 18 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
clang/lib/Driver/Driver.cpp
View File

@ -774,6 +774,18 @@ void Driver::CreateOffloadingDeviceToolChains(Compilation &C,
llvm::Triple TT(Val);
std::string NormalizedName = TT.normalize();
// We want to expand the shortened versions of the triples passed in to
// the values used for the bitcode libraries for convenience.
if (TT.getVendor() == llvm::Triple::UnknownVendor ||
TT.getOS() == llvm::Triple::UnknownOS) {
if (TT.getArch() == llvm::Triple::nvptx)
TT = llvm::Triple("nvptx-nvidia-cuda");
else if (TT.getArch() == llvm::Triple::nvptx64)
TT = llvm::Triple("nvptx64-nvidia-cuda");
else if (TT.getArch() == llvm::Triple::amdgcn)
TT = llvm::Triple("amdgcn-amd-amdhsa");
}
// Make sure we don't have a duplicate triple.
auto Duplicate = FoundNormalizedTriples.find(NormalizedName);
if (Duplicate != FoundNormalizedTriples.end()) {

10
clang/test/Driver/fat_archive_nvptx.cpp
View File

@ -6,9 +6,9 @@
// Given a FatArchive, clang-offload-bundler should be called to create a
// device specific archive, which should be passed to clang-nvlink-wrapper.
// RUN: %clang -O2 -### -fopenmp -fopenmp-targets=nvptx64 %s -L%S/Inputs/openmp_static_device_link -lFatArchive 2>&1 | FileCheck %s
// CHECK: clang{{.*}}"-cc1"{{.*}}"-triple" "nvptx64"{{.*}}"-target-cpu" "[[GPU:sm_[0-9]+]]"{{.*}}"-o" "[[HOSTBC:.*.s]]" "-x" "c++"{{.*}}.cpp
// CHECK: clang-offload-bundler" "-unbundle" "-type=a" "-inputs={{.*}}/Inputs/openmp_static_device_link/libFatArchive.a" "-targets=openmp-nvptx64-[[GPU]]" "-outputs=[[DEVICESPECIFICARCHIVE:.*.a]]" "-allow-missing-bundles"
// RUN: %clang -O2 -### -fopenmp -fopenmp-targets=nvptx64-nvidia-cuda %s -L%S/Inputs/openmp_static_device_link -lFatArchive 2>&1 | FileCheck %s
// CHECK: clang{{.*}}"-cc1"{{.*}}"-triple" "nvptx64-nvidia-cuda"{{.*}}"-target-cpu" "[[GPU:sm_[0-9]+]]"{{.*}}"-o" "[[HOSTBC:.*.s]]" "-x" "c++"{{.*}}.cpp
// CHECK: clang-offload-bundler" "-unbundle" "-type=a" "-inputs={{.*}}/Inputs/openmp_static_device_link/libFatArchive.a" "-targets=openmp-nvptx64-nvidia-cuda-[[GPU]]" "-outputs=[[DEVICESPECIFICARCHIVE:.*.a]]" "-allow-missing-bundles"
// CHECK: clang-nvlink-wrapper{{.*}}"-o" "{{.*}}.out" "-arch" "[[GPU]]" "{{.*}}[[DEVICESPECIFICARCHIVE]]"
// expected-no-diagnostics
@ -72,8 +72,8 @@ void func_present(float* in, float* out, unsigned n){
clang -O2 -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx908 -c func_1.c -o func_1_gfx908.o
clang -O2 -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx906 -c func_2.c -o func_2_gfx906.o
clang -O2 -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx908 -c func_2.c -o func_2_gfx908.o
clang -O2 -fopenmp -fopenmp-targets=nvptx64 -c func_1.c -o func_1_nvptx.o
clang -O2 -fopenmp -fopenmp-targets=nvptx64 -c func_2.c -o func_2_nvptx.o
clang -O2 -fopenmp -fopenmp-targets=nvptx64-nvidia-cuda -c func_1.c -o func_1_nvptx.o
clang -O2 -fopenmp -fopenmp-targets=nvptx64-nvidia-cuda -c func_2.c -o func_2_nvptx.o
2. Create a fat archive by combining all the object file(s)
llvm-ar cr libFatArchive.a func_1_gfx906.o func_1_gfx908.o func_2_gfx906.o func_2_gfx908.o func_1_nvptx.o func_2_nvptx.o

2
openmp/libomptarget/DeviceRTL/CMakeLists.txt
View File

@ -227,7 +227,7 @@ endfunction()
# Generate a Bitcode library for all the compute capabilities the user requested
foreach(sm ${nvptx_sm_list})
compileDeviceRTLLibrary(sm_${sm} nvptx -target nvptx64 -Xclang -target-feature -Xclang +ptx61 "-D__CUDA_ARCH__=${sm}0")
compileDeviceRTLLibrary(sm_${sm} nvptx -target nvptx64-nvidia-cuda -Xclang -target-feature -Xclang +ptx61 "-D__CUDA_ARCH__=${sm}0")
endforeach()
foreach(mcpu ${amdgpu_mcpus})