[PATCH] D22821: AMDGPU: Use rcp for fdiv 1, x with fpmath metadata

[Matt Arsenault via llvm-commits]

arsenm created this revision.
arsenm added reviewers: tstellarAMD, mareko.
arsenm added a subscriber: llvm-commits.
Herald added subscribers: kzhuravl, arsenm.

Using rcp should be OK for safe math usually, so this
should not be replacing the original fdiv.

https://reviews.llvm.org/D22821

Files:
  lib/Target/AMDGPU/AMDGPUCodeGenPrepare.cpp
  test/CodeGen/AMDGPU/amdgpu-codegenprepare.ll
  test/CodeGen/AMDGPU/rcp-pattern.ll
  test/CodeGen/AMDGPU/reciprocal.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D22821.65552.patch
Type: text/x-patch
Size: 6781 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20160726/6292c0a1/attachment.bin>