[PATCH] D130817: [X86][FP16] Fix vector_shuffle and lowering without f16c feature problems

[Phoebe Wang via Phabricator via llvm-commits]

pengfei created this revision.
pengfei added reviewers: alexfh, skan, LuoYuanke, craig.topper, RKSimon.
Herald added subscribers: StephenFan, hiraditya.
Herald added a project: All.
pengfei requested review of this revision.
Herald added a project: LLVM.
Herald added a subscriber: llvm-commits.

The problem Alexander reported on D127982 <https://reviews.llvm.org/D127982> was caused by an optimization
for AVX512-FP16 instruction. We must limit it to the feature enabled only.

During the investigation, I found we didn't expand for fp_round/fp_extend
without F16C. This may result runtime crash, so change them too.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D130817

Files:
  llvm/lib/Target/X86/X86ISelLowering.cpp
  llvm/test/CodeGen/X86/half.ll
  llvm/test/CodeGen/X86/vector-half-conversions.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D130817.448771.patch
Type: text/x-patch
Size: 236738 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20220730/afa1c822/attachment-0001.bin>