[all-commits] [llvm/llvm-project] 31eaf8: [SLP]Improve minbitwidth analysis.

[Alexey Bataev via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 31eaf86a1e8f1870e6ee4c42088a5213bde294b8
      https://github.com/llvm/llvm-project/commit/31eaf86a1e8f1870e6ee4c42088a5213bde294b8
  Author: Alexey Bataev <5361294+alexey-bataev at users.noreply.github.com>
  Date:   2024-03-19 (Tue, 19 Mar 2024)

  Changed paths:
    M llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
    M llvm/test/Transforms/SLPVectorizer/AArch64/ext-trunc.ll
    M llvm/test/Transforms/SLPVectorizer/AArch64/gather-buildvector-with-minbitwidth-user.ll
    M llvm/test/Transforms/SLPVectorizer/AArch64/gather-with-minbith-user.ll
    M llvm/test/Transforms/SLPVectorizer/AArch64/getelementptr2.ll
    M llvm/test/Transforms/SLPVectorizer/AArch64/reduce-add-i64.ll
    M llvm/test/Transforms/SLPVectorizer/RISCV/reductions.ll
    M llvm/test/Transforms/SLPVectorizer/X86/PR35777.ll
    M llvm/test/Transforms/SLPVectorizer/X86/int-bitcast-minbitwidth.ll
    M llvm/test/Transforms/SLPVectorizer/X86/minbitwidth-icmp-to-trunc.ll
    M llvm/test/Transforms/SLPVectorizer/X86/minbitwidth-multiuse-with-insertelement.ll
    M llvm/test/Transforms/SLPVectorizer/X86/minbitwidth-transformed-operand.ll
    M llvm/test/Transforms/SLPVectorizer/X86/minbitwidth-user-not-min.ll
    M llvm/test/Transforms/SLPVectorizer/X86/minimum-sizes.ll
    M llvm/test/Transforms/SLPVectorizer/X86/phi-undef-input.ll
    M llvm/test/Transforms/SLPVectorizer/X86/resched.ll
    M llvm/test/Transforms/SLPVectorizer/X86/reused-reductions-with-minbitwidth.ll
    M llvm/test/Transforms/SLPVectorizer/X86/same-scalar-in-same-phi-extract.ll
    M llvm/test/Transforms/SLPVectorizer/X86/store-insertelement-minbitwidth.ll
    M llvm/test/Transforms/SLPVectorizer/alt-cmp-vectorize.ll

  Log Message:
  -----------
  [SLP]Improve minbitwidth analysis.

This improves overall analysis for minbitwidth in SLP. It allows to
analyze the trees with store/insertelement root nodes. Also, instead of
using single minbitwidth, detected from the very first analysis stage,
it tries to detect the best one for each trunc/ext subtree in the graph
and use it for the subtree.
Results in better code and less vector register pressure.

Metric: size..text

Program                                                                                                                                                size..text
                                                                                                                                                       results     results0    diff
                                                                      test-suite :: SingleSource/Benchmarks/Adobe-C++/simple_types_loop_invariant.test    92549.00    92609.00  0.1%
                                                                                  test-suite :: External/SPEC/CINT2017speed/625.x264_s/625.x264_s.test   663381.00   663493.00  0.0%
                                                                                   test-suite :: External/SPEC/CINT2017rate/525.x264_r/525.x264_r.test   663381.00   663493.00  0.0%
                                                                                               test-suite :: MultiSource/Benchmarks/Bullet/bullet.test   307182.00   307214.00  0.0%
                                                                             test-suite :: External/SPEC/CFP2017speed/638.imagick_s/638.imagick_s.test  1394420.00  1394484.00  0.0%
                                                                              test-suite :: External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r.test  1394420.00  1394484.00  0.0%
                                                                                test-suite :: External/SPEC/CFP2017rate/510.parest_r/510.parest_r.test  2040257.00  2040273.00  0.0%

                                                                              test-suite :: External/SPEC/CFP2017rate/526.blender_r/526.blender_r.test 12396098.00 12395858.00 -0.0%
                                                                                         test-suite :: External/SPEC/CINT2006/445.gobmk/445.gobmk.test   909944.00   909768.00 -0.0%

SingleSource/Benchmarks/Adobe-C++/simple_types_loop_invariant - 4 scalar
instructions remain scalar (good).
Spec2017/x264 - the whole function idct4x4dc is vectorized using <16
x i16> instead of <16 x i32>, also zext/trunc are removed. In other
places last vector zext/sext removed and replaced by
extractelement + scalar zext/sext pair.
MultiSource/Benchmarks/Bullet/bullet - reduce or <4 x i32> replaced by
reduce or <4 x i8>
Spec2017/imagick - Removed extra zext from 2 packs of the operations.
Spec2017/parest - Removed extra zext, replaced by extractelement+scalar
zext
Spec2017/blender - the whole bunch of vector zext/sext replaced by
extractelement+scalar zext/sext, some extra code vectorized in smaller
types.
Spec2006/gobmk - fixed cost estimation, some small code remains scalar.

Original Pull Request: https://github.com/llvm/llvm-project/pull/84334

The patch has the same functionality (no test changes, no changes in
benchmarks) as the original patch, just has some compile time
improvements + fixes for xxhash unittest, discovered earlier in the
previous version of the patch.

Reviewers:

Pull Request: https://github.com/llvm/llvm-project/pull/84536



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