diff options
| author | Pierre van Houtryve <pierre.vanhoutryve@amd.com> | 2025-07-24 12:41:57 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-07-24 12:41:57 +0200 |
| commit | cd1b84caa852bb3f5469ab3da93ccb9dfafa7089 (patch) | |
| tree | 533941bac0deb8bf3fe70080abd9517f2206fa10 /clang/lib/CodeGen | |
| parent | 1a32bcb4379fb90d2b764ac33b917de1431c6b16 (diff) | |
| download | llvm-cd1b84caa852bb3f5469ab3da93ccb9dfafa7089.zip llvm-cd1b84caa852bb3f5469ab3da93ccb9dfafa7089.tar.gz llvm-cd1b84caa852bb3f5469ab3da93ccb9dfafa7089.tar.bz2 | |
[NFC][AMDGPU] Rename "amdgpu-as" to "amdgpu-synchronize-as" (#148627)
"amdgpu-as" is way too vague and doesn't give enough context.
We may want to support it on normal atomics too, to control the synchronized (ordered) AS.
If we do that, the name has to be less vague.
Diffstat (limited to 'clang/lib/CodeGen')
| -rw-r--r-- | clang/lib/CodeGen/TargetBuiltins/AMDGPU.cpp | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/clang/lib/CodeGen/TargetBuiltins/AMDGPU.cpp b/clang/lib/CodeGen/TargetBuiltins/AMDGPU.cpp index 7dccf82..e469a01 100644 --- a/clang/lib/CodeGen/TargetBuiltins/AMDGPU.cpp +++ b/clang/lib/CodeGen/TargetBuiltins/AMDGPU.cpp @@ -274,7 +274,7 @@ llvm::Value *CodeGenFunction::EmitScalarOrConstFoldImmArg(unsigned ICEArguments, void CodeGenFunction::AddAMDGPUFenceAddressSpaceMMRA(llvm::Instruction *Inst, const CallExpr *E) { - constexpr const char *Tag = "amdgpu-as"; + constexpr const char *Tag = "amdgpu-synchronize-as"; LLVMContext &Ctx = Inst->getContext(); SmallVector<MMRAMetadata::TagT, 3> MMRAs; |