[all-commits] [llvm/llvm-project] a1d33c: AMDGPU/GlobalISel: Custom legalize v2s16 G_SHUFFLE...

[Matt Arsenault via All-commits]

  Branch: refs/heads/master
  Home:   https://github.com/llvm/llvm-project
  Commit: a1d33ce73a5e39db71e630f641423db277d1e29f
      https://github.com/llvm/llvm-project/commit/a1d33ce73a5e39db71e630f641423db277d1e29f
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2020-01-27 (Mon, 27 Jan 2020)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
    M llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.h
    M llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-shuffle-vector.mir
    A llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-shuffle-vector.s16.mir

  Log Message:
  -----------
  AMDGPU/GlobalISel: Custom legalize v2s16 G_SHUFFLE_VECTOR

Try to keep simple v2s16 cases as-is. This will more naturally map to
how the VOP3P op_sel modifiers work compared to the expansion
involving bitcasts and bitshifts.

This could maybe try harder with wider source vector types, although
that could be handled with a pre-legalize combine.