[all-commits] [llvm/llvm-project] 46aa3c: [DAG] visitVECTOR_SHUFFLE - MergeInnerShuffle - im...

[Simon Pilgrim via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 46aa3c6c331c20b8a4c358488fefab96f944e814
      https://github.com/llvm/llvm-project/commit/46aa3c6c331c20b8a4c358488fefab96f944e814
  Author: Simon Pilgrim <llvm-dev at redking.me.uk>
  Date:   2021-01-15 (Fri, 15 Jan 2021)

  Changed paths:
    M llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
    M llvm/test/CodeGen/Thumb2/mve-vmull-loop.ll
    M llvm/test/CodeGen/Thumb2/mve-vst2.ll

  Log Message:
  -----------
  [DAG] visitVECTOR_SHUFFLE - MergeInnerShuffle - improve shuffle(shuffle(x,y),shuffle(x,y)) merging

MergeInnerShuffle currently attempts to merge shuffle(shuffle(x,y),z) patterns into a single shuffle, using 1 or 2 of the x,y,z ops.

However if we already match 2 ops we might be able to handle the third op if its also a shuffle that references one of the previous ops, allowing us to handle some cases like:

shuffle(shuffle(x,y),shuffle(x,y))
shuffle(shuffle(shuffle(x,z),y),z)
shuffle(shuffle(x,shuffle(x,y)),z)
etc.

This isn't an exhaustive match and is dependent on the order the candidate ops are encountered - if one of the matched ops was a shuffle that was peek-able we don't go back and try to split that, I haven't found much need for that amount of analysis yet.

This is a preliminary patch that will allow us to later improve x86 HADD/HSUB matching - but needs to be reviewed separately as its in generic code and affects existing Thumb2 tests.

Differential Revision: https://reviews.llvm.org/D94671