[PATCH] D110557: [X86] Optimize fdiv with reciprocal instructions for half type

[Pengfei Wang via Phabricator via llvm-commits]

pengfei updated this revision to Diff 377276.
pengfei marked 2 inline comments as done.
pengfei added a comment.

Thanks Simon. I had seen the discussion about `INSERT_VECTOR_ELT` and `SCALAR_TO_VECTOR`, but forgot the conclusion. Do you remember the reason why we prefer the latter?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D110557/new/

https://reviews.llvm.org/D110557

Files:
  llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
  llvm/lib/Target/X86/X86ISelLowering.cpp
  llvm/test/CodeGen/X86/avx512fp16-arith-vl-intrinsics.ll
  llvm/test/CodeGen/X86/avx512fp16-arith.ll
  llvm/test/CodeGen/X86/avx512fp16-intrinsics.ll
  llvm/test/CodeGen/X86/avx512fp16vl-intrinsics.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D110557.377276.patch
Type: text/x-patch
Size: 9066 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20211005/ef1d78e9/attachment-0001.bin>