[all-commits] [llvm/llvm-project] 4ddc8d: [CostModel][ARM]Adjust cost of muls in (U/S)MLAL a...

[Nashe Mncube via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 4ddc8df6ca1c9c1a1f03f03baefba5d1f6e2e78b
      https://github.com/llvm/llvm-project/commit/4ddc8df6ca1c9c1a1f03f03baefba5d1f6e2e78b
  Author: Nashe Mncube <nashe.mncube at arm.com>
  Date:   2025-03-19 (Wed, 19 Mar 2025)

  Changed paths:
    M llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp
    A llvm/test/Analysis/CostModel/ARM/muls-in-smlal-patterns.ll
    A llvm/test/Analysis/CostModel/ARM/muls-in-umull-patterns.ll

  Log Message:
  -----------
  [CostModel][ARM]Adjust cost of muls in (U/S)MLAL and patterns (#122713)

PR #117350 made changes to the SLP vectorizer which introduced a
regression on some ARM benchmarks. Investigation narrowed it down to
suboptimal codegen for benchmarks that previously only used scalar (U/S)MLAL
instructions. The linked change meant the SLPVectorizer thought that
these could be vectorized. This change makes the cost of muls in
(U/S)MLAL patterns slightly cheaper to make sure scalar instructions are
preferred in these cases over SLP vectorization on targets supporting DSP



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