[PATCH] D120544: [AMDGPU] Omit unnecessary waitcnt before barriers

Austin Kerbow via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Fri Feb 25 00:55:03 PST 2022


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

It is not necessary to wait for all outstanding memory operations before
barriers on hardware that can back off of the barrier in the event of an
exception when traps are enabled. Add a new subtarget feature which
tracks which HW has this ability.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D120544

Files:
  llvm/lib/Target/AMDGPU/AMDGPU.td
  llvm/lib/Target/AMDGPU/GCNSubtarget.h
  llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
  llvm/test/CodeGen/AMDGPU/back-off-barrier-subtarget-feature.ll
  llvm/test/CodeGen/AMDGPU/waitcnt-preexisting-vscnt.mir
  llvm/test/CodeGen/AMDGPU/waitcnt-vscnt.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D120544.411342.patch
Type: text/x-patch
Size: 15554 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20220225/bc2275a5/attachment.bin>


More information about the llvm-commits mailing list