[PATCH] D23417: AMDGPU/SI: Avoid moving PHIs to VALU when phi values are defined in scalar branches

[Tom Stellard via Phabricator via llvm-commits]

tstellarAMD updated this revision to Diff 79328.
tstellarAMD marked 3 inline comments as done.
tstellarAMD added a comment.
Herald added subscribers: tony-tye, yaxunl, nhaehnle, wdng.

Address review comments.


https://reviews.llvm.org/D23417

Files:
  lib/Target/AMDGPU/SIFixSGPRCopies.cpp
  test/CodeGen/AMDGPU/branch-relaxation.ll
  test/CodeGen/AMDGPU/cf-loop-on-constant.ll
  test/CodeGen/AMDGPU/coalescer_remat.ll
  test/CodeGen/AMDGPU/lds-m0-init-in-loop.ll
  test/CodeGen/AMDGPU/loop_break.ll
  test/CodeGen/AMDGPU/uniform-cfg.ll
  test/CodeGen/AMDGPU/uniform-loop-inside-nonuniform.ll
  test/CodeGen/AMDGPU/valu-i1.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D23417.79328.patch
Type: text/x-patch
Size: 14902 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20161126/daf92725/attachment.bin>