[all-commits] [llvm/llvm-project] 7ecf19: [AMDGPU] Fix and extend vccz workarounds

[Jay Foad via All-commits]

  Branch: refs/heads/master
  Home:   https://github.com/llvm/llvm-project
  Commit: 7ecf19697ee21a23fc8782daefcb268085874d7f
      https://github.com/llvm/llvm-project/commit/7ecf19697ee21a23fc8782daefcb268085874d7f
  Author: Jay Foad <jay.foad at amd.com>
  Date:   2020-11-18 (Wed, 18 Nov 2020)

  Changed paths:
    M llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
    M llvm/test/CodeGen/AMDGPU/infinite-loop.ll
    M llvm/test/CodeGen/AMDGPU/nested-loop-conditions.ll
    M llvm/test/CodeGen/AMDGPU/si-annotate-cf.ll
    M llvm/test/CodeGen/AMDGPU/si-annotate-cfg-loop-assert.ll
    M llvm/test/CodeGen/AMDGPU/vccz-corrupt-bug-workaround.mir

  Log Message:
  -----------
  [AMDGPU] Fix and extend vccz workarounds

We have workarounds for two different cases where vccz can get out of
sync with the value in vcc. This fixes them in two ways:

1. Fix the case where the def of vcc was in a previous basic block, by
pessimistically assuming that vccz might be incorrect at a basic block
boundary.

2. Fix the handling of pre-existing waitcnt instructions by calling
generateWaitcntInstBefore before examining ScoreBrackets to determine
whether there's an outstanding smem read operation.

Differential Revision: https://reviews.llvm.org/D91636