[all-commits] [llvm/llvm-project] 6d8b07: [AArch64][GlobalISel] Enable memcpy family combine...

[Jessica Paquette via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 6d8b070d96197df6b5bf9fc2c53a78171ba64c6c
      https://github.com/llvm/llvm-project/commit/6d8b070d96197df6b5bf9fc2c53a78171ba64c6c
  Author: Jessica Paquette <jpaquette at apple.com>
  Date:   2021-05-10 (Mon, 10 May 2021)

  Changed paths:
    M llvm/lib/Target/AArch64/GISel/AArch64PreLegalizerCombiner.cpp
    M llvm/test/CodeGen/AArch64/GlobalISel/inline-memset.mir

  Log Message:
  -----------
  [AArch64][GlobalISel] Enable memcpy family combines on minsize functions

The combines in `tryCombineMemCpyFamily` have heuristics (e.g.
`TLI.getMaxStoresPerMemset`) which consider size. So, theoretically, enabling
these combines on minsize functions shouldn't be harmful.

With this enabled we save 0.9% geomean on CTMark at -Oz, and 5.1% on Bullet.
There are no code size regressions.

Differential Revision: https://reviews.llvm.org/D102198