[all-commits] [llvm/llvm-project] 0298c5: [SLP]Model reduction_add(ext(<n x i1>)) as ext(ctp...

[Alexey Bataev via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 0298c5921d3b9fbeb5fefc2555321ea82ade6090
      https://github.com/llvm/llvm-project/commit/0298c5921d3b9fbeb5fefc2555321ea82ade6090
  Author: Alexey Bataev <a.bataev at outlook.com>
  Date:   2024-11-21 (Thu, 21 Nov 2024)

  Changed paths:
    M llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
    M llvm/test/Transforms/SLPVectorizer/X86/alternate-cmp-swapped-pred.ll
    M llvm/test/Transforms/SLPVectorizer/zext-incoming-for-neg-icmp.ll

  Log Message:
  -----------
  [SLP]Model reduction_add(ext(<n x i1>)) as ext(ctpop(bitcast <n x i1> to int n))

Currently sequences reduction_add(ext(<n x i1>)) are modeled as vector
extensions + reduction add, but later instcombiner transforms it into
ext(ctcpop(bitcast <n x i1> to int n)). Patch adds direct support for
this in SLP vectorizer, which enables better cost estimation.

AVX512, -O3+LTO

CINT2006/445.gobmk - extra vector code
Prolangs-C/bison - extra vector code
Benchmarks/NPB-serial/is - 16 x + 8 x reductions vectorized as 24
x reduction

Reviewers: RKSimon

Reviewed By: RKSimon

Pull Request: https://github.com/llvm/llvm-project/pull/116875



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