[PATCH] D47782: AMDGPU: Custom lower v2f16 fneg/fabs with illegal f16

[Matt Arsenault via Phabricator via llvm-commits]

arsenm created this revision.
arsenm added reviewers: rampitec, kzhuravl, cfang.
Herald added subscribers: t-tye, tpr, dstuttard, yaxunl, nhaehnle, wdng.

Fixes terrible code on targets without f16 support. The
legalization creates a mess that is difficult to recover
from. Also should avoid randomly breaking these tests
multiple times in sequence in future commits.

      

Some regressions in cases where it happens to be better
to pull the source modifier after the conversion.


https://reviews.llvm.org/D47782

Files:
  lib/Target/AMDGPU/SIISelLowering.cpp
  lib/Target/AMDGPU/SIInstructions.td
  test/CodeGen/AMDGPU/fabs.f16.ll
  test/CodeGen/AMDGPU/fneg-fabs.f16.ll
  test/CodeGen/AMDGPU/fneg.f16.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D47782.149979.patch
Type: text/x-patch
Size: 9564 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20180605/1aa43ae2/attachment.bin>