[all-commits] [llvm/llvm-project] ef8707: [AArch64][GlobalISel] Legalize narrow scalar FP ar...

[Jessica Paquette via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: ef8707574bbc7d264644d9e6730118cc0addd871
      https://github.com/llvm/llvm-project/commit/ef8707574bbc7d264644d9e6730118cc0addd871
  Author: Jessica Paquette <jpaquette at apple.com>
  Date:   2021-08-24 (Tue, 24 Aug 2021)

  Changed paths:
    M llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp
    A llvm/test/CodeGen/AArch64/GlobalISel/legalize-fp-arith-fp16.mir

  Log Message:
  -----------
  [AArch64][GlobalISel] Legalize narrow scalar FP arithmetic

Widen narrow fp arithmetic ops (e.g. G_FADD). When we don't have full FP16
support, widen to s32. Otherwise widen to s16.

https://godbolt.org/z/TbT9Pqa7e

Differential Revision: https://reviews.llvm.org/D108660