This adds support for 64 bit buffer atomic arithmetic instructions but does not include
cmpswap as that depends on a fix to the way the register pairs are handled
Change-Id: Ib207ea65fb69487ccad5066ea647ae8ddfe2ce61
Paths
| Differential D58918
[AMDGPU] Add support for 64 bit buffer atomic artihmetic instructions ClosedPublic Authored by rtaylor on Mar 4 2019, 12:28 PM.
Details Summary This adds support for 64 bit buffer atomic arithmetic instructions but does not include Change-Id: Ib207ea65fb69487ccad5066ea647ae8ddfe2ce61
Diff Detail
Event TimelineThis comment was removed by rtaylor. This revision is now accepted and ready to land.Mar 5 2019, 10:43 AM Closed by commit rL355520: [AMDGPU] Add support for 64 bit buffer atomic artihmetic instructions (authored by rtayl). · Explain WhyMar 6 2019, 9:04 AM This revision was automatically updated to reflect the committed changes. Comment Actions
Sorry, I just saw this, not sure if you are still interested but no I do not. I haven't looked at this for a bit.
Revision Contents
Diff 189521 llvm/trunk/include/llvm/IR/IntrinsicsAMDGPU.td
llvm/trunk/lib/Target/AMDGPU/BUFInstructions.td
llvm/trunk/lib/Target/AMDGPU/SIInstrInfo.td
llvm/trunk/test/Analysis/DivergenceAnalysis/AMDGPU/llvm.amdgcn.buffer.atomic.ll
llvm/trunk/test/Analysis/LegacyDivergenceAnalysis/AMDGPU/llvm.amdgcn.buffer.atomic.ll
llvm/trunk/test/CodeGen/AMDGPU/llvm.amdgcn.buffer.atomic.ll
|