[all-commits] [llvm/llvm-project] 3ede2d: [LLVM][LV] Improve UF calculation for vscale based...

Paul Walker via All-commits all-commits at lists.llvm.org
Tue Jul 29 04:50:00 PDT 2025


  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 3ede2decbe271270e081e31ce26e3acd42de2f2c
      https://github.com/llvm/llvm-project/commit/3ede2decbe271270e081e31ce26e3acd42de2f2c
  Author: Paul Walker <paul.walker at arm.com>
  Date:   2025-07-29 (Tue, 29 Jul 2025)

  Changed paths:
    M llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
    M llvm/test/Transforms/LoopVectorize/AArch64/sve-vscale-based-trip-counts.ll

  Log Message:
  -----------
  [LLVM][LV] Improve UF calculation for vscale based scalar loops. (#146102)

Update getSmallConstantTripCount() to return scalable ElementCount
values that is used to acurrately determine the maximum value for UF,
namely:

  TripCount / VF ==> X * VScale / Y * VScale ==> X / Y

This improves the chances of being able to remove the scalar loop and
also fixes an issue where a UF=2 is choosen for a scalar loop with
exactly VF(= X * VScale) iterations.



To unsubscribe from these emails, change your notification settings at https://github.com/llvm/llvm-project/settings/notifications


More information about the All-commits mailing list