[PATCH] D19076: AMDGPU/SI: Re-implement the lowering for 32-bit floating point division

[Changpeng Fang via llvm-commits]

cfang updated this revision to Diff 55314.
cfang added a comment.

Update based on Matt's comments:

1. Keep the original fpdiv32 expansion under fast_math;
2. update the LIT test for fpdiv.ll


http://reviews.llvm.org/D19076

Files:
  lib/Target/AMDGPU/SIISelLowering.cpp
  test/CodeGen/AMDGPU/fdiv.ll
  test/CodeGen/AMDGPU/frem.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D19076.55314.patch
Type: text/x-patch
Size: 8863 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20160427/a96637f4/attachment.bin>