[all-commits] [llvm/llvm-project] c56846: [ARM] Remove FlattenVectorShuffle and add PerformV...

[David Green via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: c56846a8928f8708f56c0eb36dcd6345e312faa0
      https://github.com/llvm/llvm-project/commit/c56846a8928f8708f56c0eb36dcd6345e312faa0
  Author: David Green <david.green at arm.com>
  Date:   2023-02-05 (Sun, 05 Feb 2023)

  Changed paths:
    M llvm/lib/Target/ARM/ARMISelLowering.cpp

  Log Message:
  -----------
  [ARM] Remove FlattenVectorShuffle and add PerformVQDMULHCombine.

This removes the FlattenVectorShuffle that folds shuffles through certain
binops. This is now handled by generic DAG combines for all but ARMISD::VQDMULH
where a PerformVQDMULHCombine is added to compensate. It pushes identical
shuffles down through the operation, in a similar way to the other combines in
DAG.