[PATCH] D158368: [AMDGPU][MISCHED] GCNBalancedSchedStrategy.

[Alexander via Phabricator via llvm-commits]

alex-t created this revision.
alex-t added reviewers: rampitec, kerbowa, vpykhtin, jrbyrnes.
Herald added subscribers: foad, javed.absar, hiraditya, tpr, dstuttard, yaxunl, jvesely, kzhuravl, arsenm, qcolombet.
Herald added a project: All.
alex-t requested review of this revision.
Herald added subscribers: wangpc, wdng.
Herald added a project: LLVM.

The change implements the scheduling strategy which aims to find a reasonable trade-off between the ILP and occupancy.

  For that purpose, it computes the heuristic metric to decide if the current schedule is worth to be kept.
  This is an attempt to use the same idea as in the https://reviews.llvm.org/D139710 to replace the shouldRevertScheduling function.
  This approach avoids additional computations in compile time by means of iterative metric computation during scheduling.
  Unlike the https://reviews.llvm.org/D139710 the heuristic is applied to all scheduling stages.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D158368

Files:
  llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
  llvm/lib/Target/AMDGPU/GCNSchedStrategy.cpp
  llvm/lib/Target/AMDGPU/GCNSchedStrategy.h
  llvm/test/CodeGen/AMDGPU/gfx-callable-return-types.ll
  llvm/test/CodeGen/AMDGPU/load-global-i16.ll
  llvm/test/CodeGen/AMDGPU/machine-scheduler-sink-trivial-remats.mir
  llvm/test/CodeGen/AMDGPU/scc-clobbered-sgpr-to-vmem-spill.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D158368.551846.patch
Type: text/x-patch
Size: 102106 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230820/188d7cb7/attachment.bin>