[PATCH] D140069: [DAGCombiner] Scalarize vectorized loads that are splatted

[Luke Lau via Phabricator via llvm-commits]

luke created this revision.
luke added a reviewer: asb.
Herald added subscribers: pmatos, StephenFan, ecnelises, pengfei, sunfish, hiraditya, jgravelle-google, sbc100, dschuff.
Herald added a project: All.
luke requested review of this revision.
Herald added subscribers: llvm-commits, pcwang-thead, aheejin.
Herald added a project: LLVM.

This un-vectorizes vector loads into scalar loads whenever they are used in a shuffle_vector that are splats, since only one element from them will be accessed.
This opens up better instruction selection of splatted loads and should address a WebAssembly issue: https://github.com/llvm/llvm-project/issues/59120


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D140069

Files:
  llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
  llvm/test/CodeGen/AArch64/sve-fixed-length-splat-vector.ll
  llvm/test/CodeGen/WebAssembly/simd-vectorized-load-splat.ll
  llvm/test/CodeGen/X86/extractelement-load.ll
  llvm/test/CodeGen/X86/sse3.ll
  llvm/test/CodeGen/X86/sse41.ll
  llvm/test/CodeGen/X86/vector-shuffle-128-v2.ll
  llvm/test/CodeGen/X86/widened-broadcast.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D140069.483033.patch
Type: text/x-patch
Size: 11584 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20221215/9420d7e1/attachment-0001.bin>