Cold-Air-Networks/mirror-llvm-project
2
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 7

[Clang] Remove use of 'temporary' toolchains for offload deduction (#131332)

Browse source 
Summary:
We need a toolchain to get the GPU architectures when compiling with
OpenMP. This kind of breaks the toolchain model because these are cached
all over the place. Instead of making a new one, just create both of
them unconditionally. It's not like this is saving any work since we
still needed to create both toolchains in the earlier case.

Fixes: https://github.com/llvm/llvm-project/issues/131325
This commit is contained in:
Joseph Huber 2025-03-14 11:08:31 -05:00 committed by GitHub
parent 999700ca47
commit befb52db94
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 8 additions and 18 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

24
clang/lib/Driver/Driver.cpp
View file

@ -1040,23 +1040,15 @@ void Driver::CreateOffloadingDeviceToolChains(Compilation &C,
// We need to temporarily create these toolchains so that we can access
// tools for inferring architectures.
llvm::DenseSet<StringRef> Archs;
if (NVPTXTriple) {
auto TempTC = std::make_unique<toolchains::CudaToolChain>(
*this, *NVPTXTriple, *HostTC, C.getInputArgs());
for (StringRef Arch : getOffloadArchs(
C, C.getArgs(), Action::OFK_OpenMP, &*TempTC, true))
Archs.insert(Arch);
}
if (AMDTriple) {
auto TempTC = std::make_unique<toolchains::AMDGPUOpenMPToolChain>(
*this, *AMDTriple, *HostTC, C.getInputArgs());
for (StringRef Arch : getOffloadArchs(
C, C.getArgs(), Action::OFK_OpenMP, &*TempTC, true))
Archs.insert(Arch);
}
if (!AMDTriple && !NVPTXTriple) {
for (const std::optional<llvm::Triple> &TT : {NVPTXTriple, AMDTriple}) {
if (!TT)
continue;
auto &TC =
getOffloadToolChain(C.getInputArgs(), Action::OFK_OpenMP, *TT,
C.getDefaultToolChain().getTriple());
for (StringRef Arch :
getOffloadArchs(C, C.getArgs(), Action::OFK_OpenMP, nullptr, true))
getOffloadArchs(C, C.getArgs(), Action::OFK_OpenMP, &TC, true))
Archs.insert(Arch);
}

2
clang/test/Driver/offload-Xarch.c
View file

@ -1,5 +1,3 @@
// UNSUPPORTED: target={{.*darwin.*}}
// RUN: %clang --target=x86_64-unknown-linux-gnu -x cuda %s -Xarch_nvptx64 -O3 -S -nogpulib -nogpuinc -### 2>&1 | FileCheck -check-prefix=O3ONCE %s
// RUN: %clang -x cuda %s -Xarch_device -O3 -S -nogpulib -nogpuinc -### 2>&1 | FileCheck -check-prefix=O3ONCE %s
// RUN: %clang -x hip %s -Xarch_amdgcn -O3 -S -nogpulib -nogpuinc -### 2>&1 | FileCheck -check-prefix=O3ONCE %s