[PATCH] D156235: [MachineBlockPlacement] Remove the pad limit for no-fallthrough loops

[Momchil Velikov via Phabricator via llvm-commits]

chill created this revision.
chill added reviewers: nikic, efriedma, dmgreen, xen0n, SixWeining.
Herald added subscribers: StephenFan, hiraditya, kristof.beyls.
Herald added a project: All.
chill requested review of this revision.
Herald added a project: LLVM.
Herald added a subscriber: llvm-commits.

This patch removes the limit on how many padding bytes are allowed to
be inserted in order to align loop blocks that have no fallthrough
edges into them and are either a loop header or are preceded in the
layout by a block in a different loop.

This change gives some small performance improvements on AArch64 and
also makes benchmark results less susceptible for variations due to
block placement.


https://reviews.llvm.org/D156235

Files:
  llvm/include/llvm/CodeGen/TargetLowering.h
  llvm/lib/CodeGen/MachineBlockPlacement.cpp
  llvm/lib/CodeGen/TargetLoweringBase.cpp
  llvm/test/CodeGen/AArch64/loop-align-limit.ll
  llvm/test/CodeGen/AArch64/merge-store-dependency.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D156235.543946.patch
Type: text/x-patch
Size: 8800 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230725/48234453/attachment.bin>