[PATCH] D130329: [AMDGPU] Aggressively schedule to reduce RP in occupancy limited regions

[Austin Kerbow via Phabricator via llvm-commits]

kerbowa created this revision.
kerbowa added reviewers: rampitec, jrbyrnes, vangthao95, arsenm.
Herald added subscribers: kosarev, jsilvanus, foad, javed.absar, hiraditya, t-tye, tpr, dstuttard, yaxunl, nhaehnle, jvesely, kzhuravl.
Herald added a project: All.
kerbowa requested review of this revision.
Herald added subscribers: llvm-commits, wdng.
Herald added a project: LLVM.

By not clustering loads and adjusting heuristics to more aggressively reduce
register pressure we may be able to increase occupancy for the function if it
was dropped in a first pass scheduling.

Similarly, try to reduce spilling if register usage exceeds lower bound
occupancy.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D130329

Files:
  llvm/lib/Target/AMDGPU/GCNSchedStrategy.cpp
  llvm/lib/Target/AMDGPU/GCNSchedStrategy.h
  llvm/lib/Target/AMDGPU/GCNSubtarget.h
  llvm/test/CodeGen/AMDGPU/agpr-copy-no-free-registers.ll
  llvm/test/CodeGen/AMDGPU/debug-value-scheduler.mir
  llvm/test/CodeGen/AMDGPU/high-RP-reschedule.mir
  llvm/test/CodeGen/AMDGPU/load-global-i16.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D130329.446700.patch
Type: text/x-patch
Size: 53026 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20220722/53d80526/attachment.bin>