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

[Alexander via Phabricator via llvm-commits]

alex-t updated this revision to Diff 554427.
alex-t marked 2 inline comments as done.
alex-t added a comment.

In this version, I decided to abandon the iterative metric computation during the scheduling 
because it is impossible to predict the final total latency (schedule length) due to the bidirectional scheduling.
The full DAG traversal is needed when the scheduling is done.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D158368/new/

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: D158368.554427.patch
Type: text/x-patch
Size: 102187 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230829/c140fc85/attachment.bin>