[all-commits] [llvm/llvm-project] 5634e7: [AMDGCN][SIWholeQuadMode] Rework splitBlock/lowerK...

[Juan Manuel Martinez Caamaño via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 5634e7e2f0e446527cf00df544e5a62a3c02db52
      https://github.com/llvm/llvm-project/commit/5634e7e2f0e446527cf00df544e5a62a3c02db52
  Author: Juan Manuel Martinez Caamaño <jmartinezcaamao at gmail.com>
  Date:   2025-03-24 (Mon, 24 Mar 2025)

  Changed paths:
    M llvm/lib/Target/AMDGPU/SIWholeQuadMode.cpp
    A llvm/test/CodeGen/AMDGPU/kill-true-in-return-block.ll
    M llvm/test/CodeGen/AMDGPU/skip-if-dead.ll
    M llvm/test/CodeGen/AMDGPU/wqm.ll

  Log Message:
  -----------
  [AMDGCN][SIWholeQuadMode] Rework splitBlock/lowerKillI1/lowerKillF32 to handle case when SI_KILL_I1_TERMINATOR -1 0 is not the unique terminator

The lowerKillI1 method wrongly handled cases where it inserted a
new S_BRANCH instruction when the kill was not the only terminator,
and then tried to split the block.

`SI_KILL_I1_TERMINATOR -1,0` doesn't have any effect. Instead of
lowering to an unconditional branch, we remove the instruction and
insert an unconditional branch only if the instruction is the last
terminator. No split is needed in this case (if the last terminator
has been reached, then the whole block was processed).

Also stop generating an unconditional branch in splitBlock: this
branch was redundant since TermMI is promoted to a
terminator that fallsthrough to the next block already.

Solves SWDEV-508819



To unsubscribe from these emails, change your notification settings at https://github.com/llvm/llvm-project/settings/notifications