[PATCH] D85517: [Scheduling] Implement a new way to cluster loads/stores

[Qing Shan Zhang via Phabricator via llvm-commits]

steven.zhang updated this revision to Diff 284569.
steven.zhang added a comment.
Herald added a subscriber: mgrang.

Address comments.

It is a pity that, the increasing cluster loads/stores we saw from AMDGPU are caused that we relax the constraint by mistake. @foad Really sorry about this and thank you for pointing this out. I have cook a new test using AArch64 load/store to show the benefit from pre-ra scheduler. And it will also remove some unnecessary cluster as we see from AMDGPU's tests. Further, it fixes the problems we see if it is used in post-ra mutation.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D85517/new/

https://reviews.llvm.org/D85517

Files:
  llvm/include/llvm/CodeGen/ScheduleDAGInstrs.h
  llvm/lib/CodeGen/MachineScheduler.cpp
  llvm/test/CodeGen/AArch64/aarch64-stp-cluster.ll
  llvm/test/CodeGen/AMDGPU/callee-special-input-vgprs.ll
  llvm/test/CodeGen/AMDGPU/stack-realign.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D85517.284569.patch
Type: text/x-patch
Size: 11374 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200811/c0eed720/attachment.bin>