[PATCH] D21765: AMDGPU: Change fdiv lowering based on !fpmath metadata

[Matt Arsenault via llvm-commits]

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

If 2.5 ulp is acceptable, denormals are not required, and
isn't a reciprocal which will already be handled, replace
with a faster fdiv.
    
Simplify the lowering tests by using per function
subtarget features.

http://reviews.llvm.org/D21765

Files:
  lib/Target/AMDGPU/AMDGPU.h
  lib/Target/AMDGPU/AMDGPUCodeGenPrepare.cpp
  lib/Target/AMDGPU/AMDGPUIntrinsicInfo.cpp
  lib/Target/AMDGPU/AMDGPUIntrinsicInfo.h
  lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
  lib/Target/AMDGPU/SIISelLowering.cpp
  lib/Target/AMDGPU/SIISelLowering.h
  lib/Target/AMDGPU/SIIntrinsics.td
  test/CodeGen/AMDGPU/amdgpu-codegenprepare.ll
  test/CodeGen/AMDGPU/fdiv.ll
  test/CodeGen/AMDGPU/llvm.amdgcn.fdiv.fast.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D21765.61997.patch
Type: text/x-patch
Size: 39906 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20160627/e19e4916/attachment.bin>