[PATCH] D154528: [AMDGPU] Generate fast fp64-to-fp16 conversions in unsafe mode.

[Ivan Kosarev via Phabricator via llvm-commits]

kosarev updated this revision to Diff 539155.
kosarev added a comment.

Update description.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D154528/new/

https://reviews.llvm.org/D154528

Files:
  llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
  llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
  llvm/test/CodeGen/AMDGPU/fptrunc.f16.ll
  llvm/test/CodeGen/AMDGPU/fptrunc.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D154528.539155.patch
Type: text/x-patch
Size: 46967 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230711/07578c9f/attachment-0001.bin>