[PATCH] D31222: AMDPU: Change DivergenceAnalysis for function arguments

[Matt Arsenault via Phabricator via llvm-commits]

arsenm created this revision.
Herald added subscribers: nhaehnle, wdng.

Stop assuming all functions are kernels.


https://reviews.llvm.org/D31222

Files:
  lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
  test/Analysis/DivergenceAnalysis/AMDGPU/kernel-args.ll
  test/CodeGen/AMDGPU/amdgpu-codegenprepare-i16-to-i32.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D31222.92569.patch
Type: text/x-patch
Size: 116017 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20170321/17126d94/attachment-0001.bin>