[all-commits] [llvm/llvm-project] fde2ae: [AMDGPU] Use SDWA for 16 bit subreg copy

[Stanislav Mekhanoshin via All-commits]

  Branch: refs/heads/master
  Home:   https://github.com/llvm/llvm-project
  Commit: fde2aefa22b9be803628888a21067288c8e2636d
      https://github.com/llvm/llvm-project/commit/fde2aefa22b9be803628888a21067288c8e2636d
  Author: Stanislav Mekhanoshin <Stanislav.Mekhanoshin at amd.com>
  Date:   2020-04-17 (Fri, 17 Apr 2020)

  Changed paths:
    M llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
    M llvm/test/CodeGen/AMDGPU/lo16-hi16-physreg-copy.mir

  Log Message:
  -----------
  [AMDGPU] Use SDWA for 16 bit subreg copy

This simplifies the logic and allows to use it on GFX8.

Differential Revision: https://reviews.llvm.org/D78150