[all-commits] [llvm/llvm-project] a0ea7e: [AMDGPU] divergence patterns for the BUILD_VECTOR ...

[alex-t via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: a0ea7ec90ff859a2b1af4514adc3643d4e3ef204
      https://github.com/llvm/llvm-project/commit/a0ea7ec90ff859a2b1af4514adc3643d4e3ef204
  Author: alex-t <alexander.timofeev at amd.com>
  Date:   2022-03-21 (Mon, 21 Mar 2022)

  Changed paths:
    M llvm/lib/Target/AMDGPU/SIInstructions.td
    M llvm/test/CodeGen/AMDGPU/divergence-driven-buildvector.ll

  Log Message:
  -----------
  [AMDGPU] divergence patterns for the BUILD_VECTOR i16, undef expansion.

BUILD_VECTOR of i16 and undef gets expanded to the COPY_TO_REGCLASS.
         The latter is further lowererd to the copy instructions.
	 We need to provide the correct register class for the uniform and divergent BUILD_VECTOR nodes
	 to avoid VGPR to SGPR copies.

Reviewed By: rampitec

Differential Revision: https://reviews.llvm.org/D122068