This just seems to have been an oversight. We already supported the f64
atomic add with an explicit scope (e.g. "cta"), but not the scopeless
version.
Details
Details
Diff Detail
Diff Detail
- Repository
- rL LLVM
Paths
| Differential D39638
[NVPTX] Implement __nvvm_atom_add_gen_d builtin. ClosedPublic Authored by jlebar on Nov 5 2017, 1:00 AM.
Details Summary This just seems to have been an oversight. We already supported the f64
Diff Detail
Event TimelineHerald added subscribers: hiraditya, sanjoy, jholewinski. · View Herald TranscriptNov 5 2017, 1:00 AM This revision is now accepted and ready to land.Nov 7 2017, 1:50 PM Closed by commit rL317623: [NVPTX] Implement __nvvm_atom_add_gen_d builtin. (authored by jlebar). · Explain WhyNov 7 2017, 2:11 PM This revision was automatically updated to reflect the committed changes.
Revision Contents
Diff 121984 cfe/trunk/include/clang/Basic/BuiltinsNVPTX.def
cfe/trunk/lib/CodeGen/CGBuiltin.cpp
cfe/trunk/test/CodeGen/builtins-nvptx-ptx50.cu
llvm/trunk/include/llvm/IR/IntrinsicsNVVM.td
llvm/trunk/lib/Target/NVPTX/NVPTXISelLowering.cpp
llvm/trunk/lib/Target/NVPTX/NVPTXIntrinsics.td
llvm/trunk/test/CodeGen/NVPTX/atomics-sm60.ll
|