[PATCH] D86078: [AArch64] Improved lowering for saturating float to int.

[Bevin Hansson via Phabricator via llvm-commits]

ebevhan updated this revision to Diff 290950.
ebevhan added a comment.

Removed NativeSaturation parameter and made all lowering happen in Lower.

We only use fminnum/fmaxnum on vector-same-width saturation, and otherwise we use integer comparisons. This improves some emitted code.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D86078/new/

https://reviews.llvm.org/D86078

Files:
  llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
  llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
  llvm/lib/Target/AArch64/AArch64ISelLowering.h
  llvm/test/CodeGen/AArch64/fptosi-sat-scalar.ll
  llvm/test/CodeGen/AArch64/fptosi-sat-vector.ll
  llvm/test/CodeGen/AArch64/fptoui-sat-scalar.ll
  llvm/test/CodeGen/AArch64/fptoui-sat-vector.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D86078.290950.patch
Type: text/x-patch
Size: 209639 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200910/d244def7/attachment-0001.bin>