[PATCH] D62802: [RFC][AMDGPU] Uniform values being used outside loop marked non-divergent

[Nicolai Hähnle via Phabricator via llvm-commits]

nhaehnle created this revision.
nhaehnle added reviewers: arsenm, dstuttard, tpr, chandlerc, rtaylor.
Herald added subscribers: t-tye, yaxunl, mgorny, wdng, jvesely, kzhuravl.
Herald added a project: LLVM.

Introduce a collection of cross-module pass IDs, currently for only a
single pass, to allow a pass to be marked as preserved from a pass in
a different module.

The remainder of the patch fixes an issue in the AMDGPU backend where
values are uniform inside of a loop but the uses of that value outside
the loop can be divergent.

Change-Id: Ic8c9c24be9e317c40001baae2e68a8a8f40055dd


Repository:
  rL LLVM

https://reviews.llvm.org/D62802

Files:
  include/llvm/CodeGen/StackProtector.h
  include/llvm/IR/Passes.h
  lib/CodeGen/StackProtector.cpp
  lib/IR/CMakeLists.txt
  lib/IR/Passes.cpp
  lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp
  lib/Transforms/Utils/LCSSA.cpp

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D62802.202660.patch
Type: text/x-patch
Size: 5645 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20190603/6968e311/attachment.bin>