[PATCH] D153279: [AMDGPU] Reimplement the GFX11 early release VGPRs optimization

[Jay Foad via Phabricator via llvm-commits]

foad created this revision.
foad added reviewers: AMDGPU, nhaehnle, rampitec, stepthomas, rovka.
Herald added subscribers: StephenFan, kerbowa, hiraditya, tpr, dstuttard, yaxunl, jvesely, kzhuravl, arsenm.
Herald added a project: All.
foad requested review of this revision.
Herald added subscribers: llvm-commits, wdng.
Herald added a project: LLVM.

Implement this optimization in SIInsertWaitcnts, where we already have
information about whether there might be outstanding VMEM store
instructions. This has the following advantages:

- Correctly handles atomics-with-return.
- Correctly handles call instructions.
- Should be faster because it does not require running a separate pass.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D153279

Files:
  llvm/lib/Target/AMDGPU/AMDGPU.h
  llvm/lib/Target/AMDGPU/AMDGPUReleaseVGPRs.cpp
  llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
  llvm/lib/Target/AMDGPU/CMakeLists.txt
  llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
  llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.global.atomic.csub.ll
  llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.image.atomic.dim.ll
  llvm/test/CodeGen/AMDGPU/call-argument-types.ll
  llvm/test/CodeGen/AMDGPU/cc-update.ll
  llvm/test/CodeGen/AMDGPU/llc-pipeline.ll
  llvm/test/CodeGen/AMDGPU/llvm.amdgcn.s.buffer.load.ll
  llvm/test/CodeGen/AMDGPU/release-vgprs.mir
  llvm/test/CodeGen/AMDGPU/waitcnt-preexisting-vscnt.mir

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D153279.532654.patch
Type: text/x-patch
Size: 37811 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230619/ed36284a/attachment.bin>