[all-commits] [llvm/llvm-project] 0d5989: [AMDGPU] Split R600 and GCN bfe patterns

[Jay Foad via All-commits]

  Branch: refs/heads/master
  Home:   https://github.com/llvm/llvm-project
  Commit: 0d5989bb24934802a9e6fcca63848a57a91efcc8
      https://github.com/llvm/llvm-project/commit/0d5989bb24934802a9e6fcca63848a57a91efcc8
  Author: Jay Foad <jay.foad at amd.com>
  Date:   2020-10-05 (Mon, 05 Oct 2020)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPUInstructions.td
    M llvm/lib/Target/AMDGPU/EvergreenInstructions.td
    M llvm/lib/Target/AMDGPU/SIInstructions.td

  Log Message:
  -----------
  [AMDGPU] Split R600 and GCN bfe patterns

This is in preparation for making the GCN patterns divergence-aware.
NFC.

Differential Revision: https://reviews.llvm.org/D88579


  Commit: 16778b19f2c2756a9e0dd04636fb2c269f684917
      https://github.com/llvm/llvm-project/commit/16778b19f2c2756a9e0dd04636fb2c269f684917
  Author: Jay Foad <jay.foad at amd.com>
  Date:   2020-10-05 (Mon, 05 Oct 2020)

  Changed paths:
    M llvm/lib/Target/AMDGPU/SIInstructions.td
    M llvm/test/CodeGen/AMDGPU/amdgpu.private-memory.ll
    M llvm/test/CodeGen/AMDGPU/bfe-patterns.ll
    M llvm/test/CodeGen/AMDGPU/llvm.amdgcn.ubfe.ll

  Log Message:
  -----------
  [AMDGPU] Make bfe patterns divergence-aware

This tends to increase code size but more importantly it reduces vgpr
usage, and could avoid costly readfirstlanes if the result needs to be
in an sgpr.

Differential Revision: https://reviews.llvm.org/D88580


Compare: https://github.com/llvm/llvm-project/compare/64b879ae2a8a...16778b19f2c2