[PATCH] D71293: AMDGPU: Generate the correct sequence of code for FDIV32 when correctly-rounded-divide-sqrt is set

[Changpeng Fang via Phabricator via llvm-commits]

cfang created this revision.
cfang added reviewers: b-sumner, arsenm.
Herald added subscribers: hiraditya, t-tye, tpr, dstuttard, yaxunl, nhaehnle, wdng, jvesely, kzhuravl.
Herald added a project: LLVM.

As the name suggests, correctly-rounded-divide-sqrt specifies the result of divion/sqrt to be rounded, and
thus we need to generate the correct sequence of code even when we flush the denormals.


https://reviews.llvm.org/D71293

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

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D71293.233153.patch
Type: text/x-patch
Size: 4788 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20191210/17be75b6/attachment-0001.bin>