[all-commits] [llvm/llvm-project] d1a7bf: [AMDGPU] Fix AMDGPUUnifyDivergentExitNodes

[Piotr Sobczak via All-commits]

  Branch: refs/heads/master
  Home:   https://github.com/llvm/llvm-project
  Commit: d1a7bfca74365c6523e647fcedd84f8fa1972dd3
      https://github.com/llvm/llvm-project/commit/d1a7bfca74365c6523e647fcedd84f8fa1972dd3
  Author: Piotr Sobczak <Piotr.Sobczak at amd.com>
  Date:   2020-03-18 (Wed, 18 Mar 2020)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPUUnifyDivergentExitNodes.cpp
    M llvm/test/CodeGen/AMDGPU/multi-divergent-exit-region.ll
    M llvm/test/CodeGen/AMDGPU/update-phi.ll

  Log Message:
  -----------
  [AMDGPU] Fix AMDGPUUnifyDivergentExitNodes

Summary:
For the case where "done" bits on existing exports are removed
by unifyReturnBlockSet(), unify all return blocks - even the
uniformly reached ones. We do not want to end up with a non-unified,
uniformly reached block containing a normal export with the "done"
bit cleared.

That case is believed to be rare - possible with infinite loops
in pixel shaders.

This is a fix for D71192.

Subscribers: arsenm, kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, kerbowa, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D76364