[all-commits] [llvm/llvm-project] 248eaf: [AArch64] SVE implies fullfp16

[Eli Friedman via All-commits]

  Branch: refs/heads/master
  Home:   https://github.com/llvm/llvm-project
  Commit: 248eaff823725fd35816b3486526a4515fb7c885
      https://github.com/llvm/llvm-project/commit/248eaff823725fd35816b3486526a4515fb7c885
  Author: Eli Friedman <efriedma at quicinc.com>
  Date:   2020-02-24 (Mon, 24 Feb 2020)

  Changed paths:
    M llvm/lib/Target/AArch64/AArch64.td
    M llvm/test/CodeGen/AArch64/sve-vector-splat.ll

  Log Message:
  -----------
  [AArch64] SVE implies fullfp16

This is explicitly guaranteed in ARMARM. And it makes reasoning about
vectors easier: we can assume that if a vector operation is legal, the
corresponding scalar operation is also legal.

Differential Revision: https://reviews.llvm.org/D74993